fetch_rss_feeds
Fetch and parse all registered RSS/Atom feeds (or specific URLs). New articles are stored in SQLite with is_new=1 for digest generation. Previously seen articles (same source_url + link) are skipped. Returns per-feed counts and articles.
This record as markdown: /tools/io-github-homenshum-nodebench/fetch-rss-feeds.md
What fetch_rss_feeds does on Nodebench
AI agents call fetch_rss_feeds to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why fetch_rss_feeds is rated Low
This tool retrieves data from RSS/Atom feeds and stores metadata in a local SQLite database. While it does write to local storage (marking articles as new), the primary action is reading/fetching feed content. The write operations are internal bookkeeping (is_new flags, storage in SQLite) to track state, not user-facing data modification.
From the tool's definition Fetch and parse all registered RSS/Atom feeds... Returns per-feed counts and articles. Data is stored but the tool itself retrieves and parses feeds without modifying external sources.
Attacks that exploit this kind of access
The rule that runs fetch_rss_feeds safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fetch_rss_feeds, this is the rule to start with:
fetch_rss_feeds is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every fetch_rss_feeds call is checked against it from then on.
Questions about fetch_rss_feeds
Fetch and parse all registered RSS/Atom feeds (or specific URLs). New articles are stored in SQLite with is_new=1 for digest generation. Previously seen articles (same source_url + link) are skipped. Returns per-feed counts and articles. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for fetch_rss_feeds: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Nodebench. Nothing to install.
fetch_rss_feeds is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the fetch_rss_feeds rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for fetch_rss_feeds. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
fetch_rss_feeds is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue